@inproceedings{zhu-etal-2024-efficient, title = "Efficient End-to-End Visual Document Understanding with Rationale Distillation", author = "Zhu, Wang and Agarwal, Alekh and Joshi, Mandar and Jia, Robin and Thomason, Jesse and Toutanova, Kristina", editor = "Duh, Kevin and Gomez, Helena and Bethard, Steven", booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)", month = jun, year = "2024", address = "Mexico City, Mexico", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.naacl-long.465/", doi = "10.18653/v1/2024.naacl-long.465", pages = "8401--8424" }